{"id":"https://openalex.org/W2215189433","doi":"https://doi.org/10.1109/bigdata.2015.7363756","title":"Evaluating cloud frameworks on genomic applications","display_name":"Evaluating cloud frameworks on genomic applications","publication_year":2015,"publication_date":"2015-10-01","ids":{"openalex":"https://openalex.org/W2215189433","doi":"https://doi.org/10.1109/bigdata.2015.7363756","mag":"2215189433"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2015.7363756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009800962","display_name":"Michele Bertoni","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Bertoni","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048332811","display_name":"Stefano Ceri","orcid":"https://orcid.org/0000-0003-0671-2415"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Ceri","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016603624","display_name":"Abdulrahman Kaitoua","orcid":"https://orcid.org/0000-0002-0244-9691"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Abdulrahman Kaitoua","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074094001","display_name":"Pietro Pinoli","orcid":"https://orcid.org/0000-0001-9786-2851"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Pinoli","raw_affiliation_strings":["Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia"],"affiliations":[{"raw_affiliation_string":"Department of Electronics, Information and Bioengineering Politecnico di Milano, Milano, Italia","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5009800962"],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":10.6864,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.98049799,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"193","last_page":"202"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9969000220298767,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7835910320281982},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7627942562103271},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6977999806404114},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.680001437664032},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6499310731887817},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.5670150518417358},{"id":"https://openalex.org/keywords/data-management","display_name":"Data management","score":0.549575686454773},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.5311065316200256},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4338217079639435},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4220616817474365},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.34869149327278137},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3068152070045471},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.23902741074562073},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.22828301787376404},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09534820914268494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0785830020904541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7835910320281982},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7627942562103271},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6977999806404114},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.680001437664032},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6499310731887817},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.5670150518417358},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.549575686454773},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5311065316200256},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4338217079639435},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4220616817474365},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.34869149327278137},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3068152070045471},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23902741074562073},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.22828301787376404},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09534820914268494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0785830020904541},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata.2015.7363756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2015.7363756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/988477","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/988477","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1036050411","https://openalex.org/W1800630092","https://openalex.org/W1976821017","https://openalex.org/W2036971997","https://openalex.org/W2065783627","https://openalex.org/W2080752853","https://openalex.org/W2098935637","https://openalex.org/W2102130607","https://openalex.org/W2117798581","https://openalex.org/W2121810937","https://openalex.org/W2128016314","https://openalex.org/W2131975293","https://openalex.org/W2139072600","https://openalex.org/W2142434250","https://openalex.org/W2142680014","https://openalex.org/W2146620757","https://openalex.org/W2147869723","https://openalex.org/W2150159606","https://openalex.org/W2158485828","https://openalex.org/W2189371416","https://openalex.org/W2259938310","https://openalex.org/W2407906562","https://openalex.org/W2963391732","https://openalex.org/W6659655122","https://openalex.org/W6679815717","https://openalex.org/W6713902681"],"related_works":["https://openalex.org/W2468279273","https://openalex.org/W2354198838","https://openalex.org/W1989130879","https://openalex.org/W2103419012","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W2844620057"],"abstract_inverted_index":{"We":[0],"are":[1,61],"developing":[2],"a":[3,31,80,109],"new,":[4],"holistic":[5],"data":[6,73,89,100,126],"management":[7,90,101,127],"system":[8],"for":[9,15,70,88],"genomics,":[10],"which":[11],"uses":[12],"cloud-based":[13],"computing":[14,34],"querying":[16],"thousands":[17],"of":[18,111,135,156,162,164],"heterogeneous":[19],"genomic":[20,121,137,165],"datasets.":[21],"In":[22,103],"our":[23,40,52,98,125],"project,":[24],"it":[25],"is":[26],"essential":[27],"to":[28,38,78,96],"leverage":[29],"upon":[30,118],"modern":[32],"cloud":[33],"framework,":[35],"so":[36],"as":[37],"encode":[39],"query":[41],"expressions":[42],"into":[43],"high-level":[44,86],"operations":[45],"provided":[46],"by":[47],"the":[48,112,133,136,152,157],"framework.":[49],"After":[50],"releasing":[51],"first":[53],"implementation":[54],"using":[55,139],"Pig":[56],"and":[57,65,129,141,147,149,154],"Hadoop":[58],"1,":[59],"we":[60,106,131],"currently":[62],"targeting":[63],"Spark":[64,76],"Flink,":[66],"two":[67,113],"emerging":[68],"frameworks":[69,114],"general-purpose":[71],"big":[72],"analytics.":[74],"While":[75],"appears":[77],"have":[79],"stronger":[81],"critical":[82],"mass,":[83],"Flink":[84,140],"supports":[85],"optimization":[87],"operations;":[91],"both":[92],"systems":[93],"appear":[94],"suited":[95],"support":[97],"domain-specific":[99],"operations.":[102],"this":[104],"paper,":[105],"focus":[107],"on":[108],"comparison":[110],"at":[115],"work":[116],"based":[117],"three":[119],"typical":[120],"applications,":[122],"stemming":[123],"from":[124],"requirements":[128],"needs;":[130],"describe":[132],"coding":[134],"applications":[138],"Spark,":[142],"discuss":[143],"their":[144],"common":[145],"aspects":[146],"differences,":[148],"comparatively":[150],"evaluate":[151],"performance":[153],"scalability":[155],"implementations":[158],"over":[159],"datasets":[160],"consisting":[161],"billions":[163],"regions.":[166]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
